EEG-VARNet: An Advanced Deep Learning Model for AccuratePrediction and Classification of Major Depressive Disorder Using EEG Data

The correct and early identification of Major Depressive Disorder (MDD) is challenging because of its complicated causes and symptoms that are similar to those of other mental diseases. This study introduces a new method for forecasting and categorizing MDD by utilizing EEG data, with a specific emphasis on Valence and Arousal measurements. Our approach combines sophisticated methods for extracting and selecting features with deeplearning models. Firstly, EEG signals are subjected to preprocessing in order to eliminate artifacts and standardize the quality of the data. The Boruta algorithm is utilized to extract features, which are then selected using the improved Cuckoo Search Algorithm. The suggested model, referred to as EEG-VARNet, utilizes two CNN models (Xception V4) and an SVM classifier to capture both spatial and temporal dependencies present in the EEG data. The model undergoes hyperparameter adjustment to maximize performance. The results of our study show substantial enhancements in the prediction of MDD with an accuracy rate of $\mathbf{9 8 . 2 \%}$, a precision rate of $96.43 \%$, and a recall rate of $\mathbf{9 7 . 8 9 \%}$. The measurements demonstrate the model's exceptional ability to diagnose MDD, emphasizing its promise as a dependable tool for clinical use.